This classification task is performed using PyTorch library of Python.
This Project is done using Google Colaboratory. The provided dataset(from udacity for an AI project. can be downloaded from here https://s3.amazonaws.com/content.udacity-data.com/nd089/flower_data.tar.gz) contains flower images of 102 categories. Training images are 6552, validation images are 818 and test images are 819. I have achieved top1 accuracy 95.73% and top5 accuracy 99.63% on test set. This project is done using Transfer learning techniques with a ResNet18(pretrained on imagenet). You can get more details in the notebook file. I have used GPU for training provided freely by Google Colaboratory(Thanks to Google for such a tremendous free online GPU support).